PeopleofSuperintelligence

Researcher

Yin Cui

Also known as 崔崟, Y. Cui

Yin Cui is a computer vision researcher whose work spans cross-view geolocalization, class-balanced learning, dataset design and open-vocabulary segmentation. They coauthored a ground-to-aerial vision paper in 2015, organized the 2017 COCO object-detection challenge at Cornell Tech, and earned a computer science PhD at Cornell University and Cornell Tech in 2019. They published Class-Balanced Loss for long-tailed learning, Fashionpedia for apparel segmentation, Simple Copy-Paste for instance segmentation and OpenSeg for open-vocabulary segmentation. The COCO dataset team shared the 2023 PAMI Mark Everingham Prize with Cui among its contributors; they held research-scientist roles at Google and NVIDIA and worked on NVIDIA's Cosmos Reason project in August 2025. As of October 2026, they are a research scientist at Meta Superintelligence Labs and serve as area chair for ICML and CVPR in 2026.

Works
93
Badges

Publication numbers from OpenAlex, as of 22 October 2026. Citations and h-index are hidden because this OpenAlex record may be incomplete or mix in other authors.

Timeline

  1. 2015–2019

    Geolocalization, COCO and a PhD

    In 2015, they coauthor a CVPR paper that learns a feature representation for matching ground-level images with aerial imagery. At Cornell Tech, they organize the 2017 COCO object-detection challenge. They complete a computer science PhD at Cornell University and Cornell Tech in 2019, advised by Serge Belongie, and coauthor the 2019 Class-Balanced Loss paper, which reweights training with the effective number of samples in each class.

  2. 2020

    Fashionpedia for apparel vision

    In 2020, they coauthor Fashionpedia, an apparel ontology and dataset with instance-segmentation masks and fine-grained attributes.

  3. 2021

    Copy-Paste for instance segmentation

    At CVPR 2021, they coauthor Simple Copy-Paste, which studies randomly pasting objects onto images for instance segmentation.

  4. 2022

    OpenSeg for open-vocabulary vision

    In 2022, they coauthor OpenSeg, which organizes images into regions indicated by arbitrary text and aligns caption words with predicted segmentation masks.

  5. 2023

    A PAMI prize for COCO

    With the COCO dataset team, they receive the 2023 PAMI Mark Everingham Prize for developing and maintaining the dataset.

  6. August 2025

    Cosmos Reason at NVIDIA

    In August 2025, they work as a research scientist on NVIDIA's Cosmos Reason project, which focuses on giving models common-sense knowledge about the physical world. Before joining Meta, they work as a research scientist at Google.

  7. 2026

    Area chair for ICML and CVPR

    They serve as area chair for ICML and CVPR in 2026.

  8. As of October 2026

    Research at Meta Superintelligence Labs

    They are a research scientist at Meta Superintelligence Labs.

Career

  1. NowMeta Superintelligence LabsResearch Scientist
  2. Until 2025NVIDIAResearch Scientist
  3. GoogleResearch Scientist

Education

  1. 2019Cornell UniversityPhD

From the biography.

  1. Of 943 people shaping AI who worked at Google, 446 work there nowIncludes Yin Cui. Our estimates of where the 943 people shaping AI who worked at Google and Google DeepMind work now: 446 at Google and 452 across 278 other organizations.
  2. 16% of AI career moves in the 2020s went from a university to a companyIncludes Yin Cui. We estimate that 16% of AI career moves in the 2020s went from a university to a company; 29% of moves starting at a university went to a company, and 76% ended the university role.
  3. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Meta. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  4. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Meta Superintelligence Labs. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Yin Cui yet. Send us a free-licensed photo.

  1. Learning Deep Representations for Ground-to-Aerial Geolocalization openaccess.thecvf.com. Checked 20 October 2026.
  2. COCO 2017 Object Detection Task cocodataset.org. Checked 20 October 2026.
  3. Yin Cui ycui.me. Checked 20 October 2026.
  4. Class-Balanced Loss Based on Effective Number of Samples arxiv.org. Checked 20 October 2026.
  5. Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset arxiv.org. Checked 20 October 2026.
  6. Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation arxiv.org. Checked 20 October 2026.
  7. Scaling Open-Vocabulary Image Segmentation with Image-Level Labels arxiv.org. Checked 20 October 2026.
  8. PAMI Mark Everingham Prize tc.computer.org. Checked 20 October 2026.
  9. How Do You Teach an AI Model to Reason? With Humans blogs.nvidia.com. Checked 20 October 2026.